© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61235
    Prev
    Next
    INDEX
    Explanations

    paths and file names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     область
    0.61
    ᄄ
    0.61
     அல்லது
    0.60
     లేదా
    0.59
     અથવા
    0.59
     или
    0.58
     റിപ്പോ
    0.58
     обслу
    0.58
     llevo
    0.57
     точно
    0.57
    POSITIVE LOGITS
     c
    0.72
     a
    0.70
     e
    0.68
     j
    0.66
     g
    0.65
     J
    0.64
     up
    0.64
     shoes
    0.64
    1
    0.63
    š
    0.63
    Activations Density 0.001%

    No Known Activations